Japanese Lexical Complexity for Non-Native Readers: a New Dataset

自然言語処理

Yusuke Ide, Masato Mita, Adam Nohejl, Hiroki Ouchi, Taro Watanabe

ACL2023 Workshop (BEA)

iMixer: invertible, implicit, and iterative MLP-Mixer from modern Hopfield networks

機械学習

Toshihiro Ota, Masato Taki

MIRU 2023

Garment Model Extraction from Clothed Mannequin Scan

コンピュータグラフィックス

Qiqi Gao, Takafumi Taketomi

Computer Graphics Forum

iMixer: hierarchical Hopfield network implies an invertible, implicit and iterative MLP-Mixer

Machine Learning

Toshihiro Ota, Masato Taki

arXiv プレプリント

Last-Iterate Convergence with Full and Noisy Feedback in Two-Player Zero-Sum Games

強化学習

Kenshi Abe, Kaito Ariu, Mitsuki Sakamoto, Kentaro Toyoshima, Atsushi Iwasaki

AISTATS 2023

LayoutDM: Discrete Diffusion Model for Controllable Layout Generation

コンピュータビジョン

Naoto Inoue, Kotaro Kikuchi, Edgar Simo-Serra, Mayu Otani, Kota Yamaguchi

CVPR 2023

Towards Flexible Multi-modal Document Models

コンピュータビジョン

Naoto Inoue, Kotaro Kikuchi, Edgar Simo-Serra, Mayu Otani, Kota Yamaguchi

CVPR 2023

Structured State Space Decoder for Speech Recognition and Synthesis

音声認識

Koichi Miyazaki, Masato Murata, Tomoki Koriyama

ICASSP 2023

Attention in a family of Boltzmann machines emerging from modern Hopfield networks

Machine Learning

Toshihiro Ota, Ryo Karakida

Neural Computation

Makeup Extraction of 3D Representation via Illumination-Aware Image Decomposition

コンピュータグラフィックス

Xingchao Yang, Takafumi Taketomi, Yoshihiro Kanamori

Computer Graphics Forum (Eurographics2023)

Gap Preserving Reductions between Reconfiguration Problems

理論計算機科学

Naoto Ohsaka

40th International Symposium on Theoretical Aspects of Computer Science (STACS 2023)

Generative Colorization of Structured Mobile Web Pages

マルチメディア

Kotaro Kikuchi, Naoto Inoue, Mayu Otani, Edgar Simo-Serra, Kota Yamaguchi

WACV 2023

More Persuasive Explanation Method For End-to-End Driving Models

接客対話エージェント

Chenkai Zhang, Daisuke Deguchi, Yuki Okafuji, Hiroshi Murase

IEEE Access 2023

Out for In!: Empirical Study on the Combination Power of Two Service Robots for Product Recommendation

接客対話エージェント

Sichao Song, Jun Baba, Yuki Okafuji, Junya Nakanishi, Yuichiro Yoshikawa, Hiroshi Ishiguro

HRI2023

Color Recommendation for Vector Graphic Documents based on Multi-Palette Representation

コンピュータビジョン

Qianru Qiu, Xueting Wang, Mayu Otani, Yuki Iwazaki

WACV 2023

Contrastive Losses Are Natural Criteria for Unsupervised Video Summarization

コンピュータビジョン

Zongshang Pang, Yuta Nakashima, Mayu Otani, Hajime Nagahara

WACV 2023

Cloze Quality Estimation for Language Assessment

自然言語処理

Zizheng Zhang, Masato Mita, Mamoru Komachi

EACL2023 (Findings)

日本語文法誤り訂正のための誤用タグ付き評価コーパスの構築

自然言語処理

小山 碧海, 喜友名 朝視顕, 小林 賢治, 新井 美桜, 三田 雅人, 岡 照晃, 小町 守

自然言語処理論文誌

On Reconfigurability of Target Sets

理論計算機科学

Naoto Ohsaka

Theoretical Computer Science

Studying the Role of Self and External Touch in the Appropriation of Dysmorphic Hands

接客対話エージェント

Antonin Cheymol, Rebecca Fribourg, Nami Ogawa, Anatole Lécuyer, Yutaro Hirao, Takuji Narumi, Ferran Argelaguet, Jean-Marie Normand

ISMAR 2022

Chinese Grammatical Error Correction Using Pre-trained Models and Pseudo Data

自然言語処理

Hongfei Wang, Michiki Kurosawa, Satoru Katsumata, Masato Mita, Mamoru Komachi

Transactions on Asian and Low-Resource Language Information Processing (TALIP)